{"id":"https://openalex.org/W4408353520","doi":"https://doi.org/10.1109/icassp49660.2025.10889518","title":"Alignment-Free Training for Transducer-based Multi-Talker ASR","display_name":"Alignment-Free Training for Transducer-based Multi-Talker ASR","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353520","doi":"https://doi.org/10.1109/icassp49660.2025.10889518"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099732902","display_name":"Shota Horiguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033975068","display_name":"Takanori Ashihara","orcid":"https://orcid.org/0009-0003-4322-4127"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanori Ashihara","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049917170","display_name":"Hiroshi Sat\u014d","orcid":"https://orcid.org/0000-0002-5899-1340"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Sato","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000803465","display_name":"Kohei Matsuura","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Matsuura","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.8880000114440918,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.8880000114440918,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.8129000067710876,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7394999861717224,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.75752854347229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6381755471229553},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5550320148468018},{"id":"https://openalex.org/keywords/hands-free","display_name":"Hands free","score":0.42264890670776367},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41055363416671753},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.35107967257499695},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08418005704879761}],"concepts":[{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.75752854347229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6381755471229553},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5550320148468018},{"id":"https://openalex.org/C3018339088","wikidata":"https://www.wikidata.org/wiki/Q28460","display_name":"Hands free","level":2,"score":0.42264890670776367},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41055363416671753},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.35107967257499695},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08418005704879761},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2407080277","https://openalex.org/W2747874407","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963240019","https://openalex.org/W2963979492","https://openalex.org/W2972362771","https://openalex.org/W2972474532","https://openalex.org/W2973091309","https://openalex.org/W3013139777","https://openalex.org/W3015190365","https://openalex.org/W3015194534","https://openalex.org/W3020336359","https://openalex.org/W3097777922","https://openalex.org/W3109079702","https://openalex.org/W3152221657","https://openalex.org/W3161873870","https://openalex.org/W3162847598","https://openalex.org/W3163560333","https://openalex.org/W3186652349","https://openalex.org/W3196194966","https://openalex.org/W3200955206","https://openalex.org/W4221147513","https://openalex.org/W4224920409","https://openalex.org/W4226098957","https://openalex.org/W4226491018","https://openalex.org/W4296069345","https://openalex.org/W4297841445","https://openalex.org/W4297841877","https://openalex.org/W4319663602","https://openalex.org/W4372259971","https://openalex.org/W4372260044","https://openalex.org/W4372260231","https://openalex.org/W4372266855","https://openalex.org/W4372267461","https://openalex.org/W4385823399","https://openalex.org/W4387010481","https://openalex.org/W4392903212","https://openalex.org/W4392904528","https://openalex.org/W4400621939","https://openalex.org/W6638523607","https://openalex.org/W6638749077"],"related_works":["https://openalex.org/W2012283803","https://openalex.org/W4384820447","https://openalex.org/W2072454424","https://openalex.org/W2383068986","https://openalex.org/W2090275562","https://openalex.org/W3152005513","https://openalex.org/W2020960496","https://openalex.org/W1266100159","https://openalex.org/W2088920587","https://openalex.org/W2046074924"],"abstract_inverted_index":{"Extending":[0],"the":[1,63,71,91,110,115,134,137,140,147,183,189],"RNN":[2],"Transducer":[3],"(RNNT)":[4],"to":[5,22,62,130,180],"recognize":[6,162],"multi-talker":[7],"speech":[8,14,165],"is":[9,33,57],"essential":[10],"for":[11,65,109],"wider":[12],"automatic":[13],"recognition":[15,24],"(ASR)":[16],"applications.":[17],"Multi-talker":[18],"RNNT":[19,117],"(MT-RNNT)":[20],"aims":[21],"achieve":[23],"without":[25,154],"relying":[26,155],"on":[27,156],"costly":[28],"front-end":[29],"source":[30],"separation.":[31],"MT-RNNT":[32,111],"conventionally":[34],"implemented":[35],"using":[36],"architectures":[37],"with":[38,166],"multiple":[39,66],"encoders":[40],"or":[41,43],"decoders,":[42],"by":[44,87,124],"serializing":[45],"all":[46,84,88,163],"speakers\u2019":[47,164],"transcriptions":[48],"into":[49],"a":[50,75,104,126],"single":[51],"output":[52],"stream.":[53],"The":[54,119],"first":[55],"approach":[56,73],"computationally":[58],"expensive,":[59],"particularly":[60],"due":[61],"need":[64],"encoder":[67,171],"processing.":[68,172],"In":[69,99],"contrast,":[70],"second":[72],"involves":[74],"complex":[76],"label":[77],"generation":[78],"process,":[79],"requiring":[80],"accurate":[81,157],"timestamps":[82],"of":[83,136,142,170,182],"words":[85],"spoken":[86],"speakers":[89],"in":[90,146],"mixture,":[92],"obtained":[93],"from":[94],"an":[95],"external":[96],"ASR":[97],"system.":[98],"this":[100],"paper,":[101],"we":[102],"propose":[103],"novel":[105],"alignment-free":[106],"training":[107,190],"scheme":[108],"(MT-RNNT-AFT)":[112],"that":[113,175,181],"adopts":[114],"standard":[116],"architecture.":[118],"target":[120],"labels":[121],"are":[122],"created":[123],"appending":[125],"prompt":[127],"token":[128],"corresponding":[129],"each":[131,143],"speaker":[132],"at":[133],"beginning":[135],"transcription,":[138],"reflecting":[139],"order":[141],"speaker\u2019s":[144],"appearance":[145],"mixtures.":[148],"Thus,":[149],"MT-RNNT-AFT":[150,176],"can":[151,161],"be":[152],"trained":[153],"alignments,":[158],"and":[159],"it":[160],"just":[167],"one":[168],"round":[169],"Experiments":[173],"show":[174],"achieves":[177],"performance":[178],"comparable":[179],"state-of-the-art":[184],"alternatives,":[185],"while":[186],"greatly":[187],"simplifying":[188],"process.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
